AI Paper Atlas

Research map / Video / Video generation

RFDM: Residual Flow Diffusion Models for Video Editing

Mohammadreza Salehi, Mehdi Noroozi, Luca Morreale, Ruchika Chavhan, Malcolm Chadwick, Alberto Gil Couto Pimentel Ramos, Abhinav Mehrotra

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
predict residual flow instead of full frame (ablation)RFDM1.5 · Senorita val, global style transfererror accumulation: 0.09 -> 0.07Improved
predict residual flow instead of full frame (ablation)RFDM · DAVIS tracking (10 videos)J&F: 29.1 -> 43.6Improved
add clean previous prediction as extra input (ablation)RFDM1.5 · Senorita val, global style transferTempCon: 0.027 -> 0.009Improved
increase autoregressive frames in loss from 0 to 5 (ablation)RFDM1.5 · Senorita val, global style transferTempCon: 0.068 -> 0.007Improved
use diffusion forcing instead of teacher forcing (ablation)RFDM1.5 · Senorita val, global style transferViDreamSim: 0.38 -> 0.35Improved
use diffusion forcing instead of teacher forcing (ablation)RFDM1.5 · Senorita val, global style transfererror accumulation: 0.06 -> 0.07Hurt
update previous-frame key frame every 3 frames instead of every frame (ablation)RFDM1.5 · Senorita val, global style transfererror accumulation: 0.16 -> 0.07Improved
never update key frame (delta=0) (ablation)RFDM1.5 · Senorita val, global style transferTempCon: 0.009 -> 0.018Hurt
unroll gradients through autoregressive stages (ablation)RFDM1.5 · Senorita val, global style transferTempCon: 0.011 -> 0.009Improved
scale backbone from SD1.5 to SD3.5RFDM · Senorita test setMLLM-Judge: 6.60 -> 7.37Improved
RFDM causal autoregressive editing vs per-frame I2I baselinesRFDM3.5 · Senorita test setViDreamSim: 0.63 -> 0.20Improved
RFDM vs VidToMe on temporal consistencyRFDM3.5 · Senorita test setTempCon: 0.007 -> 0.009Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy